Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours

Paul H Kwan; Keisuke Kameyama; Kazuo Toraichi

doi:10.1109/PACRIM.2001.953571

Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours

Paul H Kwan, Keisuke Kameyama, Kazuo Toraichi

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Citations (Scopus)

Abstract

We propose an automatic retrieval method that addresses the problem of finding similar trademark images from a database when compared with an input. Our method is based on evaluating the compatibility of relative relations among extracted image contour segments between the input and the registered images using relaxation matching. The overall compatibility, after finding a best matching configuration between contour segments of the input and each registered image, provides the basis for a distance metric used in similarity ranking. Experiments were carried out on 300 randomly selected trademark images obtained from the Japan Patent Office's Website for performance evaluation. The applicability of our method, however, is not limited to trademark retrieval but can be extended to other applications having the need for image similarity matching.

Original language	English
Title of host publication	Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)
Place of Publication	Los Alamitos, United States of America
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	255-258
Volume	1
ISBN (Print)	0780370805, 0780370813
DOIs	https://doi.org/10.1109/PACRIM.2001.953571
Publication status	Published - 2001
Event	PACRIM 2001: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing - Victoria, Canada Duration: 26 Aug 2001 → 28 Aug 2001

Conference

Conference	PACRIM 2001: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing
City	Victoria, Canada
Period	26/08/01 → 28/08/01

Keywords

Image Processing
Pattern Recognition and Data Mining

Access to Document

10.1109/PACRIM.2001.953571

https://hdl.handle.net/1959.11/14117

Handle.net

Persistent link

Cite this

Kwan, P. H., Kameyama, K., & Toraichi, K. (2001). Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours. In Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM) (Vol. 1, pp. 255-258). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/PACRIM.2001.953571

Kwan, Paul H ; Kameyama, Keisuke ; Toraichi, Kazuo. / Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours. Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM). Vol. 1 Los Alamitos, United States of America : Institute of Electrical and Electronics Engineers (IEEE), 2001. pp. 255-258

@inproceedings{4776d9e96a424fe39c070b3d8bc8a3bc,

title = "Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours",

abstract = "We propose an automatic retrieval method that addresses the problem of finding similar trademark images from a database when compared with an input. Our method is based on evaluating the compatibility of relative relations among extracted image contour segments between the input and the registered images using relaxation matching. The overall compatibility, after finding a best matching configuration between contour segments of the input and each registered image, provides the basis for a distance metric used in similarity ranking. Experiments were carried out on 300 randomly selected trademark images obtained from the Japan Patent Office's Website for performance evaluation. The applicability of our method, however, is not limited to trademark retrieval but can be extended to other applications having the need for image similarity matching.",

keywords = "Image Processing, Pattern Recognition and Data Mining",

author = "Kwan, \{Paul H\} and Keisuke Kameyama and Kazuo Toraichi",

year = "2001",

doi = "10.1109/PACRIM.2001.953571",

language = "English",

isbn = "0780370805",

volume = "1",

pages = "255--258",

booktitle = "Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "PACRIM 2001: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing ; Conference date: 26-08-2001 Through 28-08-2001",

}

Kwan, PH, Kameyama, K & Toraichi, K 2001, Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours. in Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM). vol. 1, Institute of Electrical and Electronics Engineers (IEEE), Los Alamitos, United States of America, pp. 255-258, PACRIM 2001: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, Victoria, Canada, 26/08/01. https://doi.org/10.1109/PACRIM.2001.953571

Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours. / Kwan, Paul H; Kameyama, Keisuke; Toraichi, Kazuo.
Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM). Vol. 1 Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE), 2001. p. 255-258.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours

AU - Kwan, Paul H

AU - Kameyama, Keisuke

AU - Toraichi, Kazuo

PY - 2001

Y1 - 2001

N2 - We propose an automatic retrieval method that addresses the problem of finding similar trademark images from a database when compared with an input. Our method is based on evaluating the compatibility of relative relations among extracted image contour segments between the input and the registered images using relaxation matching. The overall compatibility, after finding a best matching configuration between contour segments of the input and each registered image, provides the basis for a distance metric used in similarity ranking. Experiments were carried out on 300 randomly selected trademark images obtained from the Japan Patent Office's Website for performance evaluation. The applicability of our method, however, is not limited to trademark retrieval but can be extended to other applications having the need for image similarity matching.

AB - We propose an automatic retrieval method that addresses the problem of finding similar trademark images from a database when compared with an input. Our method is based on evaluating the compatibility of relative relations among extracted image contour segments between the input and the registered images using relaxation matching. The overall compatibility, after finding a best matching configuration between contour segments of the input and each registered image, provides the basis for a distance metric used in similarity ranking. Experiments were carried out on 300 randomly selected trademark images obtained from the Japan Patent Office's Website for performance evaluation. The applicability of our method, however, is not limited to trademark retrieval but can be extended to other applications having the need for image similarity matching.

KW - Image Processing

KW - Pattern Recognition and Data Mining

UR - https://www.scopus.com/pages/publications/0034780709

U2 - 10.1109/PACRIM.2001.953571

DO - 10.1109/PACRIM.2001.953571

M3 - Conference contribution

SN - 0780370805

SN - 0780370813

VL - 1

SP - 255

EP - 258

BT - Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Los Alamitos, United States of America

T2 - PACRIM 2001: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

Y2 - 26 August 2001 through 28 August 2001

ER -

Kwan PH, Kameyama K, Toraichi K. Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours. In Proceedings of the 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM). Vol. 1. Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE). 2001. p. 255-258 doi: 10.1109/PACRIM.2001.953571

Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this